Experimental study on gearbox prognosis using total life vibration analysis

The wear fault is one of the gear failure modes which most frequently happen in gearboxes. Tracking the development of wear, especially estimating the remaining usage life for early wear is a challenge in gearbox fault diagnosis and prognosis. A method to extract the feature of gearbox's signal...

Full description

Saved in:
Bibliographic Details
Main Authors: Teng Hongzhi, Zhao Jianmin, Jia Xisheng, Jia Yunxian, Zhang Xinghui, Cai Liying
Format: Conference Proceeding
Language:English
Subjects:
Choi-Williams distribution
feature extraction
gear wear
Hidden Markov models
Hidden semi-Markov model
Markov processes
remaining usage life
time-frequency analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The wear fault is one of the gear failure modes which most frequently happen in gearboxes. Tracking the development of wear, especially estimating the remaining usage life for early wear is a challenge in gearbox fault diagnosis and prognosis. A method to extract the feature of gearbox's signal is proposed and the remaining usage life is evaluated in this paper. The total life vibration signal of experimental study is taken as the research basis. Extracting features from vibration signals is carried out by Time-Frequency analysis. The rule of gear wear progression is studied using the vibration signal feature. The remaining usage life estimate is implemented by Hidden semi-Markov model. Through the total life test of gearbox, the feasibility and effectiveness of this method is verified.
ISSN:2166-563X
2166-5656
DOI:10.1109/PHM.2011.5939486